159 results about "Function computation" patented technology

The invention relates to the technical field of numerical control programming, in particular to a five-axis machining path planning method and system based on data driving, and the method comprises the following steps: obtaining real-time coordinates of each axis of a machine tool, calculating linear velocity and angular velocity components to construct a Jacobian matrix, executing singular value decomposition, and calculating a conditional number ratio by using maximum and minimum singular values; and inputting a nonlinear mapping function to calculate a dynamic penalty factor, generating a rotating shaft weighted item in combination with a rotating shaft identifier, constructing a weighted damping least square objective function, calculating a five-axis motion increment, and accumulating the five-axis motion increment with a real-time coordinate to generate a target absolute position coordinate. According to the method, the pose singularity degree is quantified by monitoring the machine tool pose condition number ratio and converted into the dynamic penalty factor to apply the self-adaptive constraint to the rotating shaft, the severe sudden change of the rotating shaft in the singularity area is inhibited, the tool nose track following error is minimized, and meanwhile smooth distribution of the motion increment is achieved; and the dynamic stability and the surface quality of five-axis linkage machining are improved.

The invention belongs to the technical field of data visualization, and particularly relates to a dynamic visualization generation method, system and device based on user behaviors and context awareness and a medium, and the method comprises the steps: generating a structured operation sequence after standardizing original input data; performing time sequence modeling on the operation sequence to generate a user behavior semantic vector, and generating a joint feature vector by adopting an attention mechanism; pre-loading an input data set, and generating a candidate view set in combination with the user intention preference in the joint feature vector; calculating view scores through a layout optimization function, and screening an optimal view scheme with the highest score; dynamically simplifying or enhancing the chart component according to the equipment performance and context parameters in the joint feature vector; calling a rendering engine to output a view, and monitoring a user interaction event; and updating the strategy network through a PPO algorithm, and optimizing a subsequent view generation path. The problem of unsmooth interaction caused by a static template is avoided, and the user experience is remarkably improved.

The invention discloses a program fault processing method, device and equipment of a software system and a storage medium, relates to the technical field of computers, can be applied to financial science and technology and medical health business scenarios, and comprises the steps that a fault knowledge graph of the software system is acquired, the fault knowledge graph is dynamically constructed based on multi-source heterogeneous data, and the fault knowledge graph is stored in a database; wherein a diversified atlas relationship is stored; performing graph neural network driven association analysis based on the system component dependency relationship and the first association relationship, mining a hidden fault propagation path on a component dependency link, and determining a fault association component and a fault root cause corresponding to the program fault data based on the hidden fault propagation path; based on the fault association component, the fault root cause and the second association relationship, determining a plurality of candidate repair schemes corresponding to the program fault data; and calculating evaluation scores of the plurality of candidate repair schemes through the utility function, sorting according to the evaluation scores, and determining an optimal repair scheme of the software system about the program fault in the plurality of candidate repair schemes.

The invention discloses an asynchronous federal learning method and system based on dynamic contribution perception and old adaptation, and the method comprises the steps: receiving a corresponding contribution degree after a server broadcasts a latest global model and a contribution degree vector; judging whether the received contribution degree meets a training condition, if so, downloading a latest global model for training, and if not, continuing to use an old version global model for training; fusing the loss function, the model deviation penalty and the old suppression item, and constructing a local optimization objective function; calculating a dynamic learning rate; and executing gradient descent to update the local model, and sending the local model to the server, so that the server performs weighted aggregation on the local model by using the dynamic aggregation weight after receiving the client local model greater than or equal to a preset number, updates the client contribution degree, and performs normalization to generate a contribution degree vector. The method gives consideration to the communication efficiency and the model precision, is suitable for a large-scale distributed machine learning scene, and has the advantages of high robustness and good adaptability.

The embodiment of the invention provides a nonlinear function calculation method and a special function calculation unit (SFU). The method comprises the following steps: determining a to-be-fitted function and a fitting interval corresponding to the to-be-fitted function; based on the to-be-fitted function and the fitting interval, configuring segment parameters and linear parameters corresponding to the to-be-fitted function; and performing fitting calculation based on the piecewise parameters and the linear parameters to obtain a first target function corresponding to the to-be-fitted function, and completing nonlinear function calculation based on the first target function. According to the invention, the problems of low precision, poor performance and low efficiency of SFU processing in the prior art are solved, and the effect of improving the SFU processing precision, efficiency and performance is achieved.

The invention discloses an intelligent stereoscopic warehouse inventory data synchronization method and device and a computer program product, and the method comprises the steps: collecting multi-source data of an intelligent stereoscopic warehouse, and constructing a multivariate data set; embedding the multivariate data set into a nonlinear mapping space, and constructing an embedded state vector for expressing inventory behaviors; a scheduling weight evaluation function is constructed based on the embedded state vector and historical error feedback, the scheduling weight of the inventory operation is calculated through the scheduling weight evaluation function, a decision is made on the synchronization mode of the inventory operation according to the scheduling weight, and the synchronization mode comprises instant synchronization, delay synchronization or merging synchronization; and based on the scheduling weight and historical error feedback, dynamically correcting the response tension coefficient of each dimension in the embedded state vector, and applying the corrected response tension coefficient to subsequent embedded state vector construction to form a feedback closed loop. According to the invention, a powerful guarantee is provided for efficient, accurate and stable operation of the intelligent warehousing system.

The embodiment of the invention provides a data processing method, which comprises the following steps of: converting an e index calculation task into an index calculation task aiming at a target fixed point number, and splitting the index calculation task aiming at the target fixed point number into a shift task and index calculation aiming at a target decimal part, an index calculation task aiming at the target decimal part is approximate to linear function calculation (namely addition and multiplication based on calculation parameters), so that the calculation process can be greatly simplified, and simple multiplication and addition are executed by utilizing a digital signal processor based on the calculation parameters corresponding to the target decimal part; compared with the prior art, the method has the advantages that operation steps and required computing resources are reduced, all computing resources of one digital signal processor are fully utilized in the process, the whole task process can be performed in series, judgment branches and data rereading do not exist, the overall computing efficiency is improved, and hardware resource consumption is reduced.

The invention discloses a quantum bit mapping method, device and equipment, a medium and a computer program product, and the method comprises the steps: calculating initial quantum bit mapping according to the mutual relation between quantum bits on which each logic gate in a quantum circuit depends; the initial quantum bit mapping is initial mapping from logic quantum bits to physical quantum bits; generating a to-be-executed gate circuit set according to the execution dependency relationship among the logic gates in the quantum circuit; based on the initial quantum bit mapping, the execution cost of each to-be-executed gate circuit in the to-be-executed gate circuit set is calculated, and the to-be-executed gate circuit with the minimum execution cost is selected as a target execution gate circuit; and based on a preset heuristic cost function, calculating costs of different SWAP strategies of the target execution gate circuit, and determining optimal quantum bit mapping according to the SWAP strategy with the minimum cost. According to the invention, the insertion of the SWAP gate in the quantum circuit is significantly reduced, so that the efficiency and precision of quantum bit mapping are improved.

The invention discloses a robot generative adversarial self-imitation learning method based on large language model feedback, and belongs to the technical field of computer systems based on specific calculation models, and the method comprises the steps: (1) initializing a strategy network, a discriminator network and a demonstration pool; (2) constructing and training a large language model feedback network: obtaining a training sample of the large language model feedback network, and training the large language model feedback network according to the training sample; and (3) an iterative learning step (33): updating the strategy network according to the reward calculated by the new cost function. According to the robot generative adversarial self-imitation learning method based on large language model feedback, the advantages of the large language model in the aspects of semantic comprehension, reasoning and knowledge organization are used as a potential award priori source, and a stable award signal can be provided when the demonstration data quality is poor, so that a strategy exceeding original demonstration is learned.

The invention discloses a hardware-based SOFTMAX function calculation method and device. The hardware-based SOFTMAX function calculation method comprises the following steps: receiving a multi-dimensional input vector corresponding to an SOFTMAX function through an input port; uniformly dividing the multi-dimensional input vector into a plurality of data segments according to an element sequence through a channel distributor, and distributing the data segments to corresponding operation channels; performing an exponential operation on the data segment using the operation channel to generate a local exponential vector; aggregating the local exponent vectors with an accumulator to generate a global exponent sum; distributing the global index sum to each operation channel, so that the operation channels generate output sub-vectors according to the local index vectors and the global index sum; and splicing the output sub-vectors according to the element sequence through a recombination unit to generate an SOFTMAX output vector. The efficient SOFTMAX function hardware acceleration calculation under the multi-channel parallel pipeline processing architecture is realized, and the calculation performance and throughput are improved by several times compared with the traditional serial software implementation.

The invention discloses a background vehicle anthropomorphic trajectory generation method for an automatic driving test scene, and the method comprises the following steps: extracting a plurality of groups of driving features in an interaction scene according to a set interaction logic, and carrying out the simulation training, so as to construct a driving simulator, driving characteristics in each group of interaction scenes are used as driving behavior data of a plurality of background vehicles, set driving styles are configured in a one-to-one correspondence manner, and a corresponding driving strategy is set for each driving style so as to construct a dynamic Bayesian game framework; the method comprises the following steps: acquiring a driving style of a background vehicle in any group of interaction scenes in real time to carry out iterative training on a multi-target utility function, calculating a profit value corresponding to the driving style of the background vehicle by utilizing the multi-target utility function, and selecting a corresponding driving strategy from a dynamic Bayesian game framework to generate a track control instruction; and performing personification optimization on the trajectory control instruction by using a random disturbance mechanism, thereby realizing multi-dimensional driving behavior dynamic generation and complex interaction logic accurate modeling.

A method, computer program product, and computer system of artificial intelligence (AI) intervention to detect and mitigate an abnormality associated with an object moving during performance of a process. A trained recurrent neural network (RNN) determines, from sensor data, a probability (Pr1) that the abnormality existed at a first time, where Pr1 exceeds a threshold T1 and in response, an alternative generative adversarial network (AGAN) determines a probability (Pa1) that the abnormality existed at the first time. A score S1, which is computed as a function of Pr1 and Pa1, exceeds T1 and in response the RNN and the AGAN determines, from the senso data, a probability (Pr2) and a probability (Pa2), respectively, that the abnormality existed at a second time. A score S2, which is computed as a function of at least Pr2, Pa2, and (S1-T1), exceeds a threshold (T2) and in response, the abnormality is mitigated.

The invention relates to the technical field of artificial intelligence and privacy protection, and discloses a vertical field large model privacy forgetting method and terminal based on double Fisher matrix guidance, and the method comprises the steps: separating two text sequence data subsets from an original training corpus of a vertical field large language model, namely a reserved data set and a forgetting data set; the reserved data set contains vertical field professional data which does not contain privacy information, and the forgotten data set contains privacy sensitive data to be eliminated. Based on an information geometry theory, calculating a reserved Fisher information matrix and a forgotten Fisher information matrix of model parameters on the reserved data set and the forgotten data set respectively; based on collaborative analysis of a reserved Fisher information matrix and a forgotten Fisher information matrix, a parameter forgotten guide function is constructed, guide function values of all parameters of a model are calculated, and a standardized guide vector is constructed according to the guide function values. According to the method, refined balance of privacy forgetting of the large language model in two levels of privacy elimination and capability keeping is realized.

The application discloses a kind of based on the difference of communication guarantee system and method of computing power service level, the system includes: computing power level construction module, priority generation module, resource scheduling module and closed loop correction module;The computing power level construction module is used to the computing power service object in the algorithm network fusion scene, constructs computing power service level vector and is disassembled into multidimensional computing power service characteristic factor, after normalization processing and weight distribution, the normalized computing power service level comprehensive vector is obtained, provide basis for subsequent computing power level and communication priority mapping, the present application relates to communication guarantee technical field.A kind of based on the difference of communication guarantee system and method of computing power service level, based on the real-time computing power uncertainty value of computing power entropy function calculation system, and combining computing power entropy gradient change rate, communication guarantee priority can be adjusted in time when computing power resource fluctuation is larger, to avoid the communication interruption or delay caused by resource fluctuation.

This disclosure provides a log data processing method, apparatus, system, device, medium, and program product, relating to the field of computer technology, and particularly to cloud computing and function computing technologies. The specific implementation scheme is as follows: the method is applied to a machine, where multiple instances run. The method includes: acquiring metadata, wherein the metadata includes resource scaling parameters and a code package, the resource scaling parameters being used to measure the timing of scaling up or down, and the code package including log data processing rules; running the code package through any target instance among the multiple instances, wherein the machine has a runtime deployed, the runtime providing a framework for running the log data processing program, and the target instance running within the framework provided by the runtime; monitoring the runtime's operating metrics, and scaling up or down the machine based on the operating metrics and resource scaling parameters. This disclosure enables flexible scaling up or down by monitoring the runtime's operating metrics.

The present invention discloses a method, apparatus, device and storage medium for running a function computing platform, belonging to the technical field of cloud services. In the present invention, by receiving function source code, when the function source code is of a target language type, it is compiled by a source code compilation component to obtain a bytecode file, and a corresponding function image is constructed, and the function image corresponding to the function source code is deployed and run through a cluster management background. The present invention changes the work of compiling and packaging function source code by the user locally to automatic processing by the function computing platform, thereby simplifying the process of the user publishing function source code, reducing the user's usage cost, and enabling the user to have a consistent experience when publishing functions in different programming languages on the platform.

The application discloses a log processing method and device, computer equipment and a storage medium, and belongs to the technical field of computers. The application filters the field data targeted by this log analysis by using filter words on the log to be analyzed, and then automatically performs business analysis on the filtered field data in a function calculation manner through an analysis function associated with a business analysis type, and outputs the final business analysis result, so that as long as the analysis function is configured, the analysis function can be introduced to implement business analysis by a machine, without manual participation in the log analysis process to troubleshoot business problems, improving the processing efficiency of the log analysis process, and enabling organic combination of log analysis and abnormal positioning and troubleshooting tasks of business logic.

This invention belongs to the field of transcendental function computation technology and discloses a resource-reusable transcendental function computation implementation device, including a preprocessing module, a table lookup module, a calculation module, and a post-processing module. The preprocessing module performs corresponding data processing according to the type of the computation function and sends the processed data to the other three modules. The table lookup module searches for the corresponding table according to the type of the computation function, obtains the polynomial coefficients, and sends them to the calculation module. The calculation module performs a finite number of multiplications and additions on the processed data from the preprocessing module and the coefficients from the table lookup module, and sends the results to the post-processing module. The post-processing module performs corresponding data post-processing according to the type of the computation function, obtains the results, and outputs them. This invention, by reusing hardware resources such as adders / subtractors and multipliers, can realize the calculation of sine, cosine, arctangent, exponential, and logarithmic functions.

Techniques for performing secure computing of softmax functions at high speed and with high accuracy are provided. A secure softmax function calculation system that calculates a share ([[softmax (u1)]], . . . , [[softmax (uJ)]]) from a share ([[u1]], . . . , [[uJ]]) includes a subtraction means for calculating a share ([[u1−u1]], [[u2−u1]], . . . , [[uJ−uJ]]), a first secure batch mapping calculation means for calculating, [[exp (u1−u1)]], [[exp (u2−u1)]], . . . , [[exp (uJ−uJ)]], an addition means for calculating a share([[∑ j=1J⁢exp⁡(uj-u1)]],… ,[[∑ j=1J⁢exp⁡(uj-uJ)]],and a second secure batch mapping calculation means for calculating a share ([[softmax (u1)], . . . , [[softmax (uJ)]]).

A computer-implemented method, computer program product, and computer system for automated model predictive control. The computer system trains multiple step look-ahead regression models, using historical states and historical actions for a to-be-optimized system, for each timestep of a past time horizon. Regression models may be either linear or nonlinear in order to capture process dynamics and nonlinearity. The computer system generates optimization constraints for each timestep of a future time horizon. The computer system generates optimization variables, based on the multiple step look-ahead regression models, for each timestep of the future time horizon. The computer system constructs a mixed integer linear programming based optimization model that includes an objective function, the optimization constraints, and the optimization variables. Nonlinear regression models are converted into piecewise linear approximation functions. The computer system solves the optimization model to produce actions for the to-be-optimized system, over the future time horizon, and recommend commitment-look-ahead actions.

The invention discloses a voice enhancement method and system based on cross-modal knowledge migration. The speech enhancement method adopted by the invention comprises the following steps: inputting a text corresponding to an audio into a large language model to obtain context-related language embedding features; performing cross-modal knowledge migration, and fusing the language embedding features into the voice embedding features to obtain cross-modal embedding features; training a speech enhancement model; calculating loss between an enhanced speech spectrum and a target speech spectrum by using a mean absolute error loss function; using a cosine similarity loss function to calculate the loss between the cross-modal embedded feature and the output of the large language model; integrating the two losses, and optimizing parameters of the speech enhancement model through a gradient descent algorithm; and in the reasoning stage, voice enhancement processing is carried out only by using the trained voice enhancement model. According to the method, the enhancement effect of the voice in the noisy environment can be effectively improved, and text data or a language model does not need to participate in the reasoning stage.

The present application relates to a kind of adaptive arctangent function computing system and method based on coprocessor, using coprocessor to complete data transmission and state control.The present application includes data write module, iteration register, iteration angle selection module, data iteration module and data write back module;Data write module reads input data from coprocessor interface and stores in iteration register;Iteration angle selection module selects optimal iteration angle according to the data characteristics in iteration register and sends to data iteration module;Data iteration module calculates iteration data according to the optimal iteration angle and iterates the state in iteration register;Data write back module sends the calculation completion signal to coprocessor and executes the calculation result write back through coprocessor interface.The present application can utilize coprocessor without changing the internal structure of processor, and also can utilize the internal logic calculation unit of processor to realize high-speed high-precision arctangent function calculation.

The embodiment of the invention provides a mirror image scanning method and device and electronic equipment. The mirror image scanning method comprises the steps of obtaining a to-be-detected file in mirror image files; splitting the to-be-detected file into a plurality of batches, and generating scanning subtasks corresponding to the batches; for each batch of scanning sub-tasks, triggering a calculation unit to load a scanning rule corresponding to the scanning sub-tasks, and executing calculation corresponding to the scanning sub-tasks according to the scanning rule, the calculation unit being realized through a function calculation FC service; and merging the calculation results corresponding to the scanning sub-tasks to obtain a mirror image scanning result. The scanning performance is improved, and the scanning time consumption is reduced.

This invention discloses a dynamic vibration reduction control method. The method involves acquiring parameter combination data of the vibration reduction equipment and inputting it into computational fluid dynamics software for calculation, outputting combined data of the results. Using the combined data of the results as independent variables and the expected loss as the dependent variable, a deep neural network is used for training to obtain a vibration loss function. An optimization algorithm is used to obtain parameter combination data with the minimum expected loss, and then an optimal vibration reduction control strategy function is constructed. The difference between the expected loss and the minimum expected loss is calculated to obtain the expected benefit. The work required to overcome external forces when the appendage switches from normal operating conditions to optimal control conditions is obtained to obtain the control cost function. An exhaustive search or swarm intelligence method is used to obtain the combination that maximizes the comprehensive evaluation function. The optimal comprehensive control strategy function under different flow velocities is obtained. The optimal comprehensive control strategy function is deployed to the controller of the vibration reduction equipment, and the relative position of the appendage is dynamically adjusted according to the measured different inflow velocities.

The invention discloses a method, a system and equipment for realizing full-link gray scale based on function calculation, and a medium. The method comprises the following steps: converting user traffic into an event through a function calculation trigger corresponding to a traffic source of the user traffic from different end sides; generating a request of a target type protocol according to a feature rule list corresponding to a traffic source and the event; and the request is forwarded to the micro-service gateway, so that the full-link gray level capability is realized. Due to the fact that flow of different protocol types can be converted into events of a uniform format by using function calculation triggers of flow sources of different end sides, and requests of a target type protocol can be obtained by combining corresponding feature rule lists, full-link gray scale can be introduced into flow scenes of different protocol types, and the flow scenes of different protocol types can be obtained. And the universality of the full-link gray scale scheme is improved.

The present application relates to the field of machine learning, and discloses a dialogue generation method, comprising: training a pre-constructed text generation model by using historical data, calculating a first loss value between a predicted reply text sequence output by the text generation model during training and a historical real reply sequence by a first loss function, calculating a second loss value between a predicted conversion rate output by the text generation model during training and a real conversion rate by a second loss function, adjusting parameters of the pre-constructed text generation model according to the first loss value and the second loss value, and obtaining a pre-trained text generation model; inputting target dialogue text, identity information of a questioning user in the target dialogue text, and identity information of a replying user into the pre-trained text generation model, and obtaining a target reply text sequence of the replying user to the target dialogue text. The present application also proposes a dialogue generation device, an electronic device and a medium. The present application can accurately generate personalized dialogue content based on natural language processing technology.

The invention relates to the field of big data stream processing, and provides a data stream conflict resolution method and device and a computer storage medium. The method comprises the following steps: receiving a data flow item; calculating a main Hash bucket index and a standby Hash bucket index of the data flow item through the first Hash function and the second Hash function to locate a main Hash bucket and a standby Hash bucket in the heavy part; searching fingerprints of data flow items in all logic units of the main hash bucket and the standby hash bucket; if the data flow items in the logic unit are found, reordering the data flow items in the logic unit according to the updated count value so as to keep descending order arrangement; if no idle logic unit exists in the main hash bucket and the standby hash bucket, executing the following conflict processing flow: selecting a data flow item with the minimum count value from the logic unit of the main hash bucket or the standby hash bucket as an expelling candidate, if the count value of the data flow item exceeds a preset threshold value, triggering a cross-bucket competition mechanism, executing cross-bucket competition, and if the count value of the data flow item exceeds the preset threshold value, executing the cross-bucket competition; and inserting the evicted data flow items into the light part for statistics.

The present invention discloses a method and system for implementing sine and cosine functions based on transcendental function acceleration instructions. The method of the present invention includes reducing each element of the incoming vector operand vd to the interval [-π / 4, π / 4] to obtain the corresponding integer vector vql and the floating-point vector vdr within the interval [-π / 4, π / 4]; taking the remainder of the integer vector vql to obtain the integer vector vqln; according to the Taylor series expansion method, using transcendental function acceleration instructions to perform polynomial approximation calculations on the floating-point vector vdr and the integer vector vqln to obtain the calculation result vr of the vector sine function or the vector cosine function. For an instruction set architecture encoded with fixed-length instructions, the present invention does not require additional address calculation instructions and vector load instructions to obtain the coefficient constants of polynomial approximation from the constant pool, thereby greatly improving the performance of the vector sine function and the vector cosine function.

The invention discloses a security reasoning method and system for privacy protection machine learning, and relates to the technical field of privacy protection machine learning, and the method comprises the steps: calculating a secret share according to a model input matrix and sand secret sharing and random vector compression secret sharing of model parameters, reconstructing a secret value and packaging to obtain TP secret sharing of a model linear layer operation result; the method comprises the following steps of: performing mask calculation on an input matrix of a nonlinear layer in TP secret sharing by adopting a random number to obtain a mask random number, calculating TP secret sharing at a first different position in bit representation of the mask random number and a required mask random number so as to determine the highest bit of the input matrix of the nonlinear layer, calculating an RELU function, and calculating a truncation result according to the RELU function, and a nonlinear layer output result is obtained based on a truncation result and a random mask in TP secret sharing, so that the communication and calculation overhead of a security reasoning online stage is reduced.

The embodiment of the invention discloses a path planning method, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring position information and task information of a storage robot; according to the position information and the task information, utilizing a prediction model to output a prediction path set; determining a target function according to the prediction path set; and calculating according to the target function to obtain a planned path, and outputting the planned path to the storage robot. Therefore, after the position of the robot can be accurately obtained, path dynamic adjustment and operation look-ahead optimization can be realized through assistance of the prediction model. According to the method, the constructed target function is iteratively solved, path planning is achieved, local optimum can be avoided, the optimal sorting path can be quickly and accurately found, meanwhile, cooperation among work of multiple robots is guaranteed through a scientific scheduling strategy, the efficient and accurate sorting requirement of the manufacturing industry is met, the logistics cost is reduced, and the delivery speed is increased.